Convergence of multi-class systems of fixed possibly infinite sizes
Carl Graham (CMAP)

TL;DR
This paper studies the convergence behavior of multi-class systems with both finite and infinite classes under partial exchangeability, revealing their sampling structure and establishing conditions for convergence of such systems.
Contribution
It characterizes the conditional law of multi-class systems with finite and infinite classes and links their convergence to the convergence of associated measure vectors.
Findings
Conditional law corresponds to independent sampling within classes
Convergence of systems is equivalent to convergence of measure vectors
Provides a framework for analyzing multi-class systems with infinite classes
Abstract
Multi-class systems having possibly both finite and infinite classes are investigated under a natural partial exchangeability assumption. It is proved that the conditional law of such a system, given the vector of the empirical measures of its finite classes and directing measures of its infinite ones (given by the de Finetti Theorem), corresponds to sampling independently from each class, without replacement from the finite classes and i.i.d. from the directing measure for the infinite ones. The equivalence between the convergence of multi-exchangeable systems with fixed class sizes and the convergence of the corresponding vectors of measures is then established.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBayesian Methods and Mixture Models · Crystallization and Solubility Studies · Statistical Distribution Estimation and Applications
